Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 47 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Super-Resolution | SET5 (test) | 192 | Apr 15, 2026 | ||
| Image Quality Assessment | CSIQ | 192 | May 19, 2026 | ||
| Person Re-identification | VIPeR | 192 | Apr 2, 2026 | ||
| Semantic Segmentation | LoveDA | 192 | May 15, 2026 | ||
| Novel View Synthesis | Mip-NeRF360 | 192 | Jun 9, 2026 | ||
| Mathematical Reasoning | AIME 2025 (test) | 191 | Jul 7, 2026 | ||
| Image Classification | ImageNet-1k 1.0 (test) | 191 | Feb 26, 2026 | ||
| text-to-audio retrieval | AudioCaps (test) | 191 | Jul 1, 2026 | ||
| Image Classification | CIFAR10 (train) | 191 | Jul 7, 2026 | ||
| 3D Object Detection | nuScenes v1.0-trainval (val) | 191 | Jul 2, 2026 | ||
| Sign Language Translation | PHOENIX-2014T (test) | 191 | Jun 11, 2026 | ||
| Trajectory Prediction | NBA (test) | 191 | Apr 28, 2026 | ||
| Person Re-identification | Market-1501 to DukeMTMC-reID (test) | 191 | Mar 17, 2026 | ||
| Action Recognition | HMDB51 | 191 | Feb 26, 2026 | ||
| General Reasoning | BBH | 190 | May 28, 2026 | ||
| Mathematical Reasoning | AIME 25 | 190 | Jun 23, 2026 | ||
| Math Reasoning | GSM8K | 190 | Jul 8, 2026 | ||
| Language Modeling | OpenWebText | 190 | Jul 2, 2026 | ||
| Multivariate long-term forecasting | Traffic | 190 | Apr 28, 2026 | ||
| Depth Super-Resolution | NYU v2 (test) | 190 | May 12, 2026 | ||
| Few-shot Image Classification | tieredImageNet | 190 | May 26, 2026 | ||
| Graph Classification | NCI1 (test) | 190 | Jul 7, 2026 | ||
| Visual Understanding | MM-Vet | 190 | Jul 7, 2026 | ||
| Performance Estimation | DIVE | 189 | Apr 28, 2026 | ||
| Black-box Attack | LSUN | 189 | Feb 26, 2026 |